diff options
Diffstat (limited to 'cmd2/parsing.py')
| -rw-r--r-- | cmd2/parsing.py | 64 |
1 files changed, 45 insertions, 19 deletions
diff --git a/cmd2/parsing.py b/cmd2/parsing.py index 908e9272..f2c86ea8 100644 --- a/cmd2/parsing.py +++ b/cmd2/parsing.py @@ -81,7 +81,7 @@ class Statement(str): return rtn -class StatementParser(): +class StatementParser: """Parse raw text into command components. Shortcuts is a list of tuples with each tuple containing the shortcut and the expansion. @@ -93,7 +93,7 @@ class StatementParser(): multiline_commands=None, aliases=None, shortcuts=None, - ): + ): self.allow_redirection = allow_redirection if terminators is None: self.terminators = [';'] @@ -144,18 +144,19 @@ class StatementParser(): # aliases have to be a word, so make a regular expression # that matches the first word in the line. This regex has two # parts, the first parenthesis enclosed group matches one - # or more non-whitespace characters, and the second group - # matches either a whitespace character or the end of the - # string. We use \A and \Z to ensure we always match the - # beginning and end of a string that may have multiple - # lines - self.command_pattern = re.compile(r'\A(\S+)(\s|\Z)') - + # or more non-whitespace characters (which may be preceeded + # by whitespace) and the second group matches either a whitespace + # character or the end of the string. We use \A and \Z to ensure + # we always match the beginning and end of a string that may have + # multiple lines + self.command_pattern = re.compile(r'\A\s*(\S+)(\s|\Z)+') def tokenize(self, line: str) -> List[str]: """Lex a string into a list of tokens. Comments are removed, and shortcuts and aliases are expanded. + + Raises ValueError if there are unclosed quotation marks. """ # strip C-style comments @@ -177,6 +178,8 @@ class StatementParser(): """Tokenize the input and parse it into a Statement object, stripping comments, expanding aliases and shortcuts, and extracting output redirection directives. + + Raises ValueError if there are unclosed quotation marks. """ # handle the special case/hardcoded terminator of a blank line @@ -297,16 +300,40 @@ class StatementParser(): return statement def parse_command_only(self, rawinput: str) -> Statement: - """Partially parse input into a Statement object. The command is - identified, and shortcuts and aliases are expanded. + """Partially parse input into a Statement object. + + The command is identified, and shortcuts and aliases are expanded. Terminators, multiline commands, and output redirection are not parsed. + + This method is used by tab completion code and therefore must not + generate an exception if there are unclosed quotes. + + The Statement object returned by this method can at most contained + values in the following attributes: + - raw + - command + - args + + Different from parse(), this method does not remove redundant whitespace + within statement.args. It does however, ensure args does not have leading + or trailing whitespace. """ - # lex the input into a list of tokens - tokens = self.tokenize(rawinput) + # expand shortcuts and aliases + line = self._expand(rawinput) - # parse out the command and everything else - (command, args) = self._command_and_args(tokens) + command = None + args = None + match = self.command_pattern.search(line) + if match: + # we got a match, extract the command + command = match.group(1) + # the command_pattern regex is designed to match the spaces + # between command and args with a second match group. Using + # the end of the second match group ensures that args has + # no leading whitespace. The rstrip() makes sure there is + # no trailing whitespace + args = line[match.end(2):].rstrip() # build the statement # string representation of args must be an empty string instead of @@ -315,7 +342,6 @@ class StatementParser(): statement.raw = rawinput statement.command = command statement.args = args - statement.argv = tokens return statement def _expand(self, line: str) -> str: @@ -342,7 +368,7 @@ class StatementParser(): # expand shortcuts for (shortcut, expansion) in self.shortcuts: - if line.startswith(shortcut): + if line.startswith(shortcut): # If the next character after the shortcut isn't a space, then insert one shortcut_len = len(shortcut) if len(line) == shortcut_len or line[shortcut_len] != ' ': @@ -370,7 +396,7 @@ class StatementParser(): if len(tokens) > 1: args = ' '.join(tokens[1:]) - return (command, args) + return command, args @staticmethod def _comment_replacer(match): @@ -387,7 +413,7 @@ class StatementParser(): # as word breaks when they are in unquoted strings. Each run of punctuation # characters is treated as a single token. - :param initial_tokens: the tokens as parsed by shlex + :param tokens: the tokens as parsed by shlex :return: the punctuated tokens """ punctuation = [] |